.gitignore
LICENSE
README.md
pyproject.toml
.github/workflows/ci.yml
.github/workflows/release.yml
docs/api-reference.md
docs/architecture.md
docs/configuration.md
docs/installation.md
docs/metrics.md
docs/quickstart.md
docs/release.md
docs/writing-tests.md
examples/agent_tests.py
examples/agent_tests_negative.py
examples/deterministic_metrics.py
examples/hello_agent.md
examples/hello_agent.py
examples/llm_judged.py
examples/multi_turn.py
src/forjinn_eval/__init__.py
src/forjinn_eval/__main__.py
src/forjinn_eval/_version.py
src/forjinn_eval/capture.py
src/forjinn_eval/cli.py
src/forjinn_eval/client.py
src/forjinn_eval/evaluators.py
src/forjinn_eval/judge.py
src/forjinn_eval/llm_metrics.py
src/forjinn_eval/plugin.py
src/forjinn_eval/py.typed
src/forjinn_eval/results.py
src/forjinn_eval/suite.py
src/forjinn_eval/types.py
src/forjinn_eval/web_scenarios.py
src/forjinn_eval.egg-info/PKG-INFO
src/forjinn_eval.egg-info/SOURCES.txt
src/forjinn_eval.egg-info/dependency_links.txt
src/forjinn_eval.egg-info/entry_points.txt
src/forjinn_eval.egg-info/requires.txt
src/forjinn_eval.egg-info/scm_file_list.json
src/forjinn_eval.egg-info/scm_version.json
src/forjinn_eval.egg-info/top_level.txt
src/forjinn_eval/catalog/__init__.py
src/forjinn_eval/catalog/attachment.py
src/forjinn_eval/catalog/base.py
src/forjinn_eval/catalog/content.py
src/forjinn_eval/catalog/llm.py
src/forjinn_eval/catalog/performance.py
src/forjinn_eval/catalog/safety.py
src/forjinn_eval/catalog/structural.py
src/forjinn_eval/catalog/tool.py
src/forjinn_eval/metrics/__init__.py
src/forjinn_eval/metrics/_common.py
src/forjinn_eval/metrics/_conversational.py
src/forjinn_eval/metrics/answer_correctness.py
src/forjinn_eval/metrics/answer_quality.py
src/forjinn_eval/metrics/answer_relevance.py
src/forjinn_eval/metrics/answer_relevancy.py
src/forjinn_eval/metrics/answer_relevancy_deepeval.py
src/forjinn_eval/metrics/attachment.py
src/forjinn_eval/metrics/base.py
src/forjinn_eval/metrics/bias.py
src/forjinn_eval/metrics/citations.py
src/forjinn_eval/metrics/composition.py
src/forjinn_eval/metrics/conformity.py
src/forjinn_eval/metrics/content.py
src/forjinn_eval/metrics/contextual.py
src/forjinn_eval/metrics/contradiction.py
src/forjinn_eval/metrics/conversational.py
src/forjinn_eval/metrics/factual_correctness.py
src/forjinn_eval/metrics/faithfulness.py
src/forjinn_eval/metrics/g_eval.py
src/forjinn_eval/metrics/goal_accuracy.py
src/forjinn_eval/metrics/groundedness.py
src/forjinn_eval/metrics/hallucination.py
src/forjinn_eval/metrics/llm_judge.py
src/forjinn_eval/metrics/loop_detection.py
src/forjinn_eval/metrics/misbehaviour.py
src/forjinn_eval/metrics/performance.py
src/forjinn_eval/metrics/pii_leakage.py
src/forjinn_eval/metrics/plan.py
src/forjinn_eval/metrics/prompt_alignment.py
src/forjinn_eval/metrics/safety.py
src/forjinn_eval/metrics/string_metrics.py
src/forjinn_eval/metrics/structural.py
src/forjinn_eval/metrics/summarization.py
src/forjinn_eval/metrics/task_completion.py
src/forjinn_eval/metrics/text_metrics.py
src/forjinn_eval/metrics/tool.py
src/forjinn_eval/metrics/tool_correctness.py
src/forjinn_eval/metrics/tool_deterministic.py
src/forjinn_eval/metrics/tool_use.py
src/forjinn_eval/metrics/topic_adherence.py
src/forjinn_eval/metrics/toxicity.py
tests/conftest.py
tests/fixtures/agent1_count.json
tests/fixtures/agent1_node_failed.json
tests/fixtures/agent1_nonstream.json
tests/fixtures/agent1_streaming.sse
tests/fixtures/agent2_tools_nonstream.json
tests/integration/__init__.py
tests/integration/test_cli_plugin.py
tests/live/__init__.py
tests/live/test_live_llm.py
tests/unit/__init__.py
tests/unit/_helpers.py
tests/unit/test_capture.py
tests/unit/test_conversational_metrics.py
tests/unit/test_deterministic.py
tests/unit/test_deterministic_metrics.py
tests/unit/test_embeddings_capture.py
tests/unit/test_llm_metrics.py
tests/unit/test_new_rag_metrics.py
tests/unit/test_results.py
tests/unit/test_suite.py
tests/unit/test_web_scenarios.py